Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DT
    -0.07
    climate
    -0.07
     rural
    -0.06
     Hàng
    -0.06
     chức
    -0.06
    活動
    -0.06
    Nu
    -0.06
    .."
    -0.06
    _MASTER
    -0.06
     disap
    -0.06
    POSITIVE LOGITS
     JMP
    0.07
     casa
    0.07
     bajo
    0.07
    (dummy
    0.07
    -j
    0.06
     ek
    0.06
    (metrics
    0.06
    Enemies
    0.06
    ,map
    0.06
    epoch
    0.06
    Act Density 0.023%

    No Known Activations